CN-121998921-A - State detection method for disconnecting link of transformer substation, electronic equipment and storage medium

CN121998921ACN 121998921 ACN121998921 ACN 121998921ACN-121998921-A

Abstract

The embodiment of the application provides a state detection method for a disconnecting link of a transformer substation, electronic equipment and a storage medium. The method comprises the steps of carrying out state detection on a plurality of images to be processed of a transformer substation disconnecting link to obtain initial opening and closing states corresponding to the images to be processed respectively, obtaining current values of the transformer substation disconnecting link at the time of collecting the images to be processed, determining a plurality of data points based on the initial opening and closing states and the current values corresponding to the images to be processed respectively, constructing a density image based on the data points, identifying according to the density image to obtain normal data points, and determining a target opening and closing state of the transformer substation disconnecting link based on the initial opening and closing states corresponding to the normal data points. The method is used for achieving the effect of improving the accuracy of state detection of the disconnecting link of the transformer substation.

Inventors

REN YUBIN
Su Daimin
ZHANG YUANYAN
XIE KAICHENG
HUANG SHUJIAN
ZHANG HUANSHEN
YANG SHIHAO
LIANG JINGTANG
XIE YONGXIANG
LIU JIANRONG
Zhuang Boming
LING QIANG

Assignees

广东电网有限责任公司惠州供电局

Dates

Publication Date: 20260508
Application Date: 20260109

Claims (10)

1. The state detection method of the disconnecting link of the transformer substation is characterized by comprising the following steps of: performing state detection on a plurality of images to be processed of a transformer substation disconnecting link to obtain initial opening and closing states respectively corresponding to the plurality of images to be processed; acquiring current values of the substation disconnecting link at the acquisition time of the plurality of images to be processed; determining a plurality of data points based on the initial opening and closing states and the current values respectively corresponding to the plurality of images to be processed; Constructing a density image based on the data points, and identifying according to the density image to obtain normal data points; and determining a target opening and closing state of the substation disconnecting link based on the initial opening and closing state corresponding to the normal data point.
2. The method of claim 1, wherein the performing state detection on the plurality of images to be processed of the substation disconnecting link to obtain initial opening and closing states respectively corresponding to the plurality of images to be processed comprises: extracting image characteristics of each image to be processed of a transformer substation disconnecting link; and carrying out state detection based on the image characteristics to obtain an initial opening and closing state corresponding to the image to be processed.
3. The method of claim 1, wherein the constructing a density image based on the plurality of data points comprises: Determining a distance parameter according to the initial opening and closing state and the current value corresponding to each data point, determining a neighborhood corresponding to the data point according to the distance parameter, and determining a density value of the data point according to the data point in the neighborhood; a density image is constructed from the density values of the plurality of data points.
4. The method of claim 1, wherein said identifying from said density image results in normal data points, comprising: Performing edge detection based on the density image to obtain an edge binary image; carrying out anomaly identification on the edge binary image through an anomaly identification model to obtain an anomaly region; Determining an outlier data point from the plurality of data points based on the outlier region; And selecting a normal data point from the plurality of data points based on the abnormal data point.
5. The method according to claim 4, wherein the method further comprises: carrying out anomaly identification on the binary image at the edge of the sample through an initial neural network model to obtain a predicted anomaly area; acquiring a predicted abnormal data point corresponding to the predicted abnormal region from sample data points corresponding to the sample edge binary image; determining an evaluation index value based on the data point label corresponding to the sample edge binary image and the predicted abnormal data point; When the evaluation index value does not meet a preset condition, adjusting parameters of the initial neural network model; and when the evaluation index value meets the preset condition, taking the initial neural network model as the abnormality identification model.
6. The method of claim 5, wherein the data point tags comprise a normal data point tag and an abnormal data point tag; the determining an evaluation index value based on the data point label corresponding to the sample edge binary image and the predicted abnormal data point comprises the following steps: Determining predicted normal data points from the sample data points and the predicted abnormal data points; Determining a first data point which is correctly predicted in the predicted abnormal data point, a second data point which is incorrectly predicted in the predicted abnormal data point, a third data point which is correctly predicted in the predicted normal data point and a fourth data point which is incorrectly predicted in the predicted normal data point according to the normal data point label, the abnormal data point label, the predicted abnormal data point and the predicted normal data point; determining an accuracy rate, a precision rate, and a recall rate according to the first data point, the second data point, the third data point, and the fourth data point; And determining a comprehensive evaluation value according to the precision rate and the recall rate, wherein the evaluation index value comprises the accuracy rate and the comprehensive evaluation value.
7. The method according to any one of claims 1 to 6, further comprising: Determining an outlier data point based on the plurality of data points and the normal data point; Classifying the abnormal data points through an abnormal classification model to obtain abnormal categories, wherein the abnormal categories are stacking abnormal categories or scattered point abnormal categories; Determining that the anomaly event is a component failure event when the anomaly category is the pile-up anomaly category; and when the anomaly category is the scattered anomaly category, determining that the anomaly event is an occasional interference event.
8. A state detection device for a substation disconnecting link, the device comprising: The first state detection module is used for carrying out state detection on a plurality of images to be processed of the transformer substation disconnecting link, and obtaining initial opening and closing states respectively corresponding to the plurality of images to be processed; The acquisition module is used for acquiring current values of the substation disconnecting link at the acquisition time of the plurality of images to be processed; the data point determining module is used for determining a plurality of data points based on the initial opening and closing states and the current values which correspond to the plurality of images to be processed respectively; The identification module is used for constructing a density image based on the data points and identifying according to the density image to obtain normal data points; and the second state detection module is used for determining a target opening and closing state of the substation disconnecting link based on the initial opening and closing state corresponding to the normal data point.
9. An electronic device comprising a processor and a memory communicatively coupled to the processor; The memory stores computer-executable instructions; The processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1 to 7.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1 to 7.

Description

State detection method for disconnecting link of transformer substation, electronic equipment and storage medium Technical Field The application relates to the technical field of power equipment detection and artificial intelligence, in particular to a state detection method of a disconnecting link of a transformer substation, electronic equipment and a storage medium. Background The transformer substation disconnecting link, also called an isolating switch, is an important device in a power system, and needs to detect the opening and closing state of the transformer substation disconnecting link in the scene of adjusting the operation mode of a circuit, equipment overhaul and the like. In the related art, the opening and closing state of the disconnecting link of the transformer substation is detected through laser ranging, but the mode is easily affected by environmental noise, so that the accuracy of state detection is low. Disclosure of Invention The embodiment of the application provides a state detection method, electronic equipment and a storage medium for a transformer substation disconnecting link, which are used for achieving the effect of improving the accuracy of state detection of the transformer substation disconnecting link. The embodiment of the application provides a state detection method of a transformer substation disconnecting link, which comprises the steps of carrying out state detection on a plurality of images to be processed of the transformer substation disconnecting link to obtain initial opening and closing states corresponding to the images to be processed respectively, obtaining current values of the transformer substation disconnecting link at the time of collecting the images to be processed, determining a plurality of data points based on the initial opening and closing states and the current values corresponding to the images to be processed respectively, constructing a density image based on the data points, identifying according to the density image to obtain normal data points, and determining a target opening and closing state of the transformer substation disconnecting link based on the initial opening and closing states corresponding to the normal data points. In a second aspect, an embodiment of the present application provides a state detection device for a disconnecting link of a substation, including: The first state detection module is used for carrying out state detection on a plurality of images to be processed of the transformer substation disconnecting link, and obtaining initial opening and closing states respectively corresponding to the plurality of images to be processed; The acquisition module is used for acquiring current values of the substation disconnecting link at the acquisition time of the plurality of images to be processed; the data point determining module is used for determining a plurality of data points based on the initial opening and closing states and the current values which correspond to the plurality of images to be processed respectively; The identification module is used for constructing a density image based on the data points and identifying according to the density image to obtain normal data points; and the second state detection module is used for determining a target opening and closing state of the substation disconnecting link based on the initial opening and closing state corresponding to the normal data point. In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, where the memory stores computer-executable instructions, and where the processor executes the computer-executable instructions stored in the memory, so that the processor executes the foregoing first aspect and/or various possible implementation manners of the first aspect. In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having stored therein computer-executable instructions for implementing the various possible implementations of the above first aspect and/or the first aspect when executed by a processor. In a fifth aspect, embodiments of the present application provide a computer program product comprising a computer program which, when executed by a processor, implements the various possible implementations of the above first aspect and/or the first aspect. According to the state detection method, the electronic equipment, the storage medium and the computer program product for the transformer substation disconnecting link, the state detection is carried out on the image to be processed of the transformer substation disconnecting link through the electronic equipment, the initial opening and closing state of the electronic equipment is obtained, the data points are determined according to the initial opening and closing state of the transformer substation disconnecting link and the current values of the transformer substation disconnectin